+#
+# Used by the web interface to link to messages outside of the our
+# public-inboxes. Mail threads may cross projects/threads; so
+# we should ensure users can find more easily find them on other
+# sites.
package PublicInbox::ExtMsg;
use strict;
use warnings;
-use URI::Escape qw(uri_escape_utf8);
-use PublicInbox::Hval;
-use PublicInbox::MID qw/mid2path/;
+use PublicInbox::Hval qw(ascii_html prurl mid_href);
+use PublicInbox::WwwStream qw(html_oneshot);
+use PublicInbox::Smsg;
+our $MIN_PARTIAL_LEN = 16;
# TODO: user-configurable
-our @EXT_URL = (
- 'http://mid.gmane.org/%s',
+our @EXT_URL = map { ascii_html($_) } (
+ # leading "//" denotes protocol-relative (http:// or https://)
+ '//marc.info/?i=%s',
+ '//www.mail-archive.com/search?l=mid&q=%s',
+ 'nntp://news.gmane.io/%s',
'https://lists.debian.org/msgid-search/%s',
- 'http://mid.mail-archive.com/%s',
- 'http://marc.info/?i=%s',
+ '//docs.FreeBSD.org/cgi/mid.cgi?db=mid&id=%s',
+ 'https://www.w3.org/mid/%s',
+ 'http://www.postgresql.org/message-id/%s',
+ 'https://lists.debconf.org/cgi-lurker/keyword.cgi?'.
+ 'doc-url=/lurker&format=en.html&query=id:%s'
);
-sub ext_msg {
- my ($ctx) = @_;
- my $pi_config = $ctx->{pi_config};
- my $listname = $ctx->{listname};
- my $mid = $ctx->{mid};
+sub PARTIAL_MAX () { 100 }
+
+sub search_partial ($$) {
+ my ($ibx, $mid) = @_;
+ return if length($mid) < $MIN_PARTIAL_LEN;
+ my $srch = $ibx->search or return;
+ my $opt = { limit => PARTIAL_MAX, mset => 2 };
+ my @try = ("m:$mid*");
+ my $chop = $mid;
+ if ($chop =~ s/(\W+)(\w*)\z//) {
+ my ($delim, $word) = ($1, $2);
+ if (length($word)) {
+ push @try, "m:$chop$delim";
+ push @try, "m:$chop$delim*";
+ }
+ push @try, "m:$chop";
+ push @try, "m:$chop*";
+ }
- eval { require PublicInbox::Search };
- my $have_xap = $@ ? 0 : 1;
- my (@nox, @pfx);
-
- foreach my $k (keys %$pi_config) {
- $k =~ /\Apublicinbox\.([A-Z0-9a-z-]+)\.url\z/ or next;
- my $list = $1;
- next if $list eq $listname;
-
- my $git_dir = $pi_config->{"publicinbox.$list.mainrepo"};
- defined $git_dir or next;
-
- my $url = $pi_config->{"publicinbox.$list.url"};
- defined $url or next;
-
- $url =~ s!/+\z!!;
-
- # try to find the URL with Xapian to avoid forking
- if ($have_xap) {
- my $s;
- my $doc_id = eval {
- $s = PublicInbox::Search->new($git_dir);
- $s->find_unique_doc_id('mid', $mid);
- };
- if ($@) {
- # xapian not configured for this repo
- } else {
- # maybe we found it!
- return r302($url, $mid) if (defined $doc_id);
-
- # no point in trying the fork fallback if we
- # know Xapian is up-to-date but missing the
- # message in the current repo
- push @pfx, { srch => $s, url => $url };
- next;
- }
+ # break out long words individually to search for, because
+ # too many messages begin with "Pine.LNX." (or "alpine" or "nycvar")
+ if ($mid =~ /\w{9,}/) {
+ my @long = ($mid =~ m!(\w{3,})!g);
+ push(@try, join(' ', map { "m:$_" } @long));
+
+ # is the last element long enough to not trigger excessive
+ # wildcard matches?
+ if (length($long[-1]) > 8) {
+ $long[-1] .= '*';
+ push(@try, join(' ', map { "m:$_" } @long));
}
+ }
- # queue up for forking after we've tried Xapian on all of them
- push @nox, { git_dir => $git_dir, url => $url };
+ foreach my $m (@try) {
+ # If Xapian can't handle the wildcard since it
+ # has too many results. $@ can be
+ # Search::Xapian::QueryParserError or even:
+ # "something terrible happened at ../Search/Xapian/Enquire.pm"
+ my $mset = eval { $srch->mset($m, $opt) } or next;
+ my @mids = map {
+ $_->{mid}
+ } @{$srch->mset_to_smsg($ibx, $mset)};
+ return \@mids if scalar(@mids);
}
+}
+
+sub ext_msg_i {
+ my ($other, $ctx) = @_;
+
+ return if $other->{name} eq $ctx->{-inbox}->{name} || !$other->base_url;
- # Xapian not installed or configured for some repos
- my $path = "HEAD:" . mid2path($mid);
+ my $mm = $other->mm or return;
- foreach my $n (@nox) {
- my @cmd = ('git', "--git-dir=$n->{git_dir}", 'cat-file',
- '-t', $path);
- my $pid = open my $fh, '-|';
- defined $pid or die "fork failed: $!\n";
+ # try to find the URL with Msgmap to avoid forking
+ my $num = $mm->num_for($ctx->{mid});
+ if (defined $num) {
+ push @{$ctx->{found}}, $other;
+ } else {
+ # no point in trying the fork fallback if we
+ # know Xapian is up-to-date but missing the
+ # message in the current repo
+ push @{$ctx->{again}}, $other;
+ }
+}
+
+sub ext_msg_step {
+ my ($pi_cfg, $section, $ctx) = @_;
+ if (defined($section)) {
+ return if $section !~ m!\Apublicinbox\.([^/]+)\z!;
+ my $ibx = $pi_cfg->lookup_name($1) or return;
+ ext_msg_i($ibx, $ctx);
+ } else { # undef == "EOF"
+ finalize_exact($ctx);
+ }
+}
- if ($pid == 0) {
- open STDERR, '>', '/dev/null'; # ignore errors
- exec @cmd or die "exec failed: $!\n";
+sub ext_msg {
+ my ($ctx) = @_;
+ sub {
+ $ctx->{-wcb} = $_[0]; # HTTP server write callback
+
+ if ($ctx->{env}->{'pi-httpd.async'}) {
+ require PublicInbox::ConfigIter;
+ my $iter = PublicInbox::ConfigIter->new(
+ $ctx->{www}->{pi_config},
+ \&ext_msg_step, $ctx);
+ $iter->event_step;
} else {
- my $type = eval { local $/; <$fh> };
- close $fh;
- if ($? == 0 && $type eq "blob\n") {
- return r302($n->{url}, $mid);
- }
+ $ctx->{www}->{pi_config}->each_inbox(\&ext_msg_i, $ctx);
+ finalize_exact($ctx);
}
- }
+ };
+}
+
+# called via PublicInbox::DS->EventLoop
+sub event_step {
+ my ($ctx, $sync) = @_;
+ # can't find a partial match in current inbox, try the others:
+ my $ibx = shift @{$ctx->{again}} or return finalize_partial($ctx);
+ my $mids = search_partial($ibx, $ctx->{mid}) or
+ return ($sync ? undef : PublicInbox::DS::requeue($ctx));
+ $ctx->{n_partial} += scalar(@$mids);
+ push @{$ctx->{partial}}, [ $ibx, $mids ];
+ $ctx->{n_partial} >= PARTIAL_MAX ? finalize_partial($ctx)
+ : ($sync ? undef : PublicInbox::DS::requeue($ctx));
+}
+
+sub finalize_exact {
+ my ($ctx) = @_;
+
+ return $ctx->{-wcb}->(exact($ctx)) if $ctx->{found};
# fall back to partial MID matching
- my $n_partial = 0;
- my @partial;
- if ($have_xap) {
- my $cgi = $ctx->{cgi};
- my $url = ref($cgi) eq 'CGI' ? $cgi->url(-base) . '/'
- : $cgi->base->as_string;
- $url .= $listname;
- unshift @pfx, { srch => $ctx->{srch}, url => $url };
- foreach my $pfx (@pfx) {
- my $srch = delete $pfx->{srch} or next;
- if (my $res = $srch->mid_prefix($mid)) {
- $n_partial += scalar(@$res);
- $pfx->{res} = $res;
- push @partial, $pfx;
- }
+ my $mid = $ctx->{mid};
+ my $cur = $ctx->{-inbox};
+ my $mids = search_partial($cur, $mid);
+ if ($mids) {
+ $ctx->{n_partial} = scalar(@$mids);
+ push @{$ctx->{partial}}, [ $cur, $mids ];
+ } elsif ($ctx->{again} && length($mid) >= $MIN_PARTIAL_LEN) {
+ bless $ctx, __PACKAGE__;
+ if ($ctx->{env}->{'pi-httpd.async'}) {
+ $ctx->event_step;
+ return;
}
+
+ # synchronous fall-through
+ $ctx->event_step while @{$ctx->{again}};
}
+ finalize_partial($ctx);
+}
+
+sub finalize_partial {
+ my ($ctx) = @_;
+ my $mid = $ctx->{mid};
my $code = 404;
- my $h = PublicInbox::Hval->new_msgid($mid, 1);
- my $href = $h->as_href;
- my $html = $h->as_html;
- my $title = "Message-ID <$html> not found";
- my $s = "$title" .
- "$title\n";
-
- if ($n_partial) {
+ my $href = mid_href($mid);
+ my $html = ascii_html($mid);
+ my $title = "<$html> not found";
+ my $s = "Message-ID <$html>\nnot found\n";
+ if (my $n_partial = $ctx->{n_partial}) {
$code = 300;
- $s.= "\nPartial matches found:\n\n";
- foreach my $pfx (@partial) {
- my $u = $pfx->{url};
- foreach my $m (@{$pfx->{res}}) {
- $h = PublicInbox::Hval->new($m);
- $href = $h->as_href;
- $html = $h->as_html;
- $s .= qq{$u/$html/\n};
+ my $es = $n_partial == 1 ? '' : 'es';
+ $n_partial .= '+' if ($n_partial == PARTIAL_MAX);
+ $s .= "\n$n_partial partial match$es found:\n\n";
+ my $cur_name = $ctx->{-inbox}->{name};
+ foreach my $pair (@{$ctx->{partial}}) {
+ my ($ibx, $res) = @$pair;
+ my $env = $ctx->{env} if $ibx->{name} eq $cur_name;
+ my $u = $ibx->base_url($env) or next;
+ foreach my $m (@$res) {
+ my $href = mid_href($m);
+ my $html = ascii_html($m);
+ $s .= qq{$u$html/\n};
}
}
}
+ my $ext = ext_urls($ctx, $mid, $href, $html);
+ if ($ext ne '') {
+ $s .= $ext;
+ $code = 300;
+ }
+ $ctx->{-html_tip} = $s .= '
';
+ $ctx->{-title_html} = $title;
+ $ctx->{-upfx} = '../';
+ $ctx->{-wcb}->(html_oneshot($ctx, $code));
+}
+
+sub ext_urls {
+ my ($ctx, $mid, $href, $html) = @_;
# Fall back to external repos if configured
- if (@EXT_URL) {
- $code = 300;
- $s .= "\nPerhaps try an external site:\n\n";
- foreach my $u (@EXT_URL) {
+ if (@EXT_URL && index($mid, '@') >= 0) {
+ my $env = $ctx->{env};
+ my $e = "\nPerhaps try an external site:\n\n";
+ foreach my $url (@EXT_URL) {
+ my $u = prurl($env, $url);
my $r = sprintf($u, $href);
my $t = sprintf($u, $html);
- $s .= qq{$t\n};
+ $e .= qq{$t\n};
}
+ return $e;
}
- $s .= '
';
-
- [300, ['Content-Type'=>'text/html; charset=UTF-8'], [$s]];
+ ''
}
-# Redirect to another public-inbox which is mapped by $pi_config
-sub r302 {
- my ($url, $mid) = @_;
- $url .= '/' . uri_escape_utf8($mid) . '/';
- [ 302,
- [ 'Location' => $url, 'Content-Type' => 'text/plain' ],
- [ "Redirecting to\n$url\n" ] ]
+sub exact {
+ my ($ctx) = @_;
+ my $mid = $ctx->{mid};
+ my $found = $ctx->{found};
+ my $href = mid_href($mid);
+ my $html = ascii_html($mid);
+ my $title = "<$html> found in ";
+ my $end = @$found == 1 ? 'another inbox' : 'other inboxes';
+ $ctx->{-title_html} = $title . $end;
+ $ctx->{-upfx} = '../';
+ my $ext_urls = ext_urls($ctx, $mid, $href, $html);
+ my $code = (@$found == 1 && $ext_urls eq '') ? 200 : 300;
+ $ctx->{-html_tip} = join('',
+ "Message-ID: <$html>\nfound in $end:\n\n",
+ (map {
+ my $u = $_->base_url;
+ qq($u$html/\n)
+ } @$found),
+ $ext_urls, '
');
+ html_oneshot($ctx, $code);
}
1;